Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/SetsunaYukiOvO/x64dbg-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/setsunayukiovo/x64dbg-mcp/dump-memory)<a href="https://agentmods.dev/commands/setsunayukiovo/x64dbg-mcp/dump-memory"><img src="https://agentmods.dev/badge/commands/setsunayukiovo/x64dbg-mcp/dump-memory/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/setsunayukiovo/x64dbg-mcp/dump-memory"><img src="https://agentmods.dev/badge/commands/setsunayukiovo/x64dbg-mcp/dump-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00005 | $0.00581 |
| Opus 5.5 | $0.00002 | $0.00232 |
| Sonnet 5.5 | $0.00001 | $0.00116 |
| Haiku 4.5 | $0.00001 | $0.00058 |
Grade A, and why
dump-memory scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a memory forensics specialist connected to x64dbg/x32dbg via MCP. Dump and analyze memory regions.
"$1" may contain an address, size, or description like "main module" or "all executable regions". If empty, provide an overview.
Phase 1: Memory Landscape
- Call
debug_get_stateto confirm the debugger is active. - Call
memory_enumeratefor a full memory map. - Call
module_listto correlate regions with loaded modules. - Call
dump_get_dumpable_regionsfor regions suitable for dumping.
Phase 2: Region Selection
If "$1" specifies an address:
5. Call memory_get_info on the address for region details (base, size, protection, type).
6. Use eval_expression if you need to compute an address from an expression.
If "$1" says "main module" or similar:
5. Call module_get_main to get the module base and size.
6. Call dump_analyze_module for detailed PE analysis.
7. Call module_get_imports to see what the module depends on.
If "$1" is empty, present options:
Dumpable Regions:
1. Main module: [name] @ 0x... ([size])
2. Heap regions: [count], total [size]
3. Executable private regions: [list] (potential unpacked/injected code)
4. Mapped files: [list]
Phase 3: Dump
For module dumps:
7. Call dump_module with module name and output path. Use the oep parameter if you know the real entry point.
For raw memory dumps:
7. Call dump_memory_region with address, size, output path, as_raw_binary: true.
Before dumping, check first 256 bytes with memory_read:
- MZ header (4D 5A) = PE file
- PK header (50 4B) = ZIP archive
- High entropy = encrypted/compressed
- ASCII text = strings/config
Phase 4: Post-Dump Verification
- If PE module: verify with
dump_analyze_module. - Use
bookmark_setto mark the dumped region's address for reference.
Report
=== Memory Dump Report ===
Region: 0x... - 0x... ([size])
Type: [module/heap/private/mapped]
Protection: [RWX]
Output: [file path]
Content: [PE/raw binary/data]
Verification:
- PE valid: [yes/no]
- Sections: [count and names]
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 72 lines · 5 tokens per session scan A 2fc459abd99e
dump-memory is a command published in the GitHub repository SetsunaYukiOvO/x64dbg-mcp (554 stars, last pushed 9d ago), licensed MIT. It adds 5 tokens to every session and 581 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
dump-memory compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dump-memorySetsunaYukiOvO/x64dbg-mcp | Command | 554 | 9d ago | MIT | A | 5 | Claude Code |
| qa-changesOpenHands/extensions | Command | 176 | yesterday | MIT | A | 63 | Claude Code |
| react-nativegetsentry/toolkit | Command | 957 | yesterday | none | A | 0 | Claude Code |
| auditar-cascadingluanpdd/kit-mcp | Command | 5 | 4d ago | MIT | A | 54 | Claude Code |
| http-serviceMadAppGang/magus | Command | 14 | yesterday | MIT | A | 27 | Claude Code |
| doctordoncheli/don-cheli-sdd | Command | 59 | 2mo ago | Apache-2.0 | A | 76 | Claude Code |
| doctorfatihkan/badi | Command | 7 | 1mo ago | MIT | A | 0 | Claude Code |